Generalized Pareto distribution
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 839
- Forks
- 220
- Avg merge
- 2d 4h
- Merged PRs (30d)
- 14
Description
Overview
Provide an implementation of the generalized Pareto distribution as described here:
- Wikipedia: generalized Pareto distribution
This distribution is often used in extreme value theory to model rare events identified as peak over threshold.
Description
Definitions in Stan of the density in the parameterization we want, as well as the cdf, lcdf, lccdf, and rng functions are available in
- @avehtari's generalized Pareto case study
Implement the following functions with full autodiff and tests.
-
gen_pareto_lpdf -
gen_pareto_lupdf -
gen_pareto_cdf -
gen_pareto_lcdf -
gen_pareto_lccdf -
gen_pareto_rng
Additional resources
-
Stan forums: generalized Pareto distribution.
-
Aki Vehtari case study generalized Pareto functions, with implementations as Stan functions
-
Stan forums technical discussion of types of reals in doc and user-defined functions
-
brms issue tracker: request generalized Pareto
Current Version:
v4.3.0
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the linked generalized Pareto case study and Stan forum discussion to confirm the requested parameterization. Then use the six named entry points—gen_pareto_lpdf, gen_pareto_lupdf, gen_pareto_cdf, gen_pareto_lcdf, gen_pareto_lccdf, and gen_pareto_rng—as the implementation checklist. Done means all functions have full autodiff support and tests covering their behavior.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100